Skip to navigation
Authors and ModelsMeta AI

Muse Glimmer 30B

Muse Glimmer 30B
Meta AI · Text Generation
POST /v1/chat/completions

Meta open 30B agentic model with image understanding, 128K context, tool calling, structured output, and controllable reasoning strength.

At a glance

FieldValue
Model idmuse-glimmer-30b
Model release date2026-08-10
Input modalitiesText, Image
Output modalitiesText
Context window128K
Weight precisionNVFP4 weights + FP8 KV
Max output tokens32,768
Featuresreasoning, vision, multimodal, function_calling, json_mode, cache
Native inferenceYes
NewNo
Structured outputJSON Schema
Supported endpointsPOST /v1/chat/completions, POST /v1/responses, POST /v1/messages, POST /v1/completions, POST /v1beta/models/muse-glimmer-30b:generateContent
Alternate model idsmeta/muse-glimmer-30b, muse-glimmer, meta-models/muse-glimmer-30b

Pricing

ChargeSpecRate
Inputper 1M prompt tokens$0.35 $0.20
Outputper 1M generated tokens$1.50 $0.80
Implicit cache readper 1M cached input tokens$0.05
Web Search (Linkup)per call when invoked$0.013

Example request

curl https://api.empiriolabs.ai/v1/chat/completions \
  -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{"model": "muse-glimmer-30b", "messages": [{"role":"user","content":"Hello"}]}'

Parameters

ParameterTypeRequiredDefaultDescription
temperaturenumberno1.0Sampling temperature. 0 is deterministic and higher values are more random. · Min: 0
top_pnumberno0.95Nucleus sampling probability mass. Lower values make outputs more focused. · Range: 0.01 – 1
max_tokensnumberno32768Maximum output tokens. · Range: 1 – 32768
stopstringno-Up to 4 strings where the model will stop generating further tokens.
reasoning_effortenumno"high"Reasoning strength level. Higher levels think longer before answering. none requests minimal thinking and max maps to the model’s xhigh strength. · Allowed: none, low, medium, high, max
top_knumberno64Limit sampling to the top K candidate tokens when supported. · Min: 1
min_pnumberno0Minimum probability threshold for token sampling. · Range: 0 – 1
frequency_penaltynumberno0Penalty based on how often a token has already appeared. · Range: -2 – 2
presence_penaltynumberno0Penalty for tokens that already appeared in the generated text. · Range: -2 – 2
response_formatenumno-Constrain the output to valid JSON. Use JSON mode for any JSON object, or supply a JSON Schema to force an exact response shape. · Allowed: text, json_object, json_schema
web_search_linkupbooleannofalseOptional web search powered by Linkup. When enabled, recent web sources are retrieved using your latest user message as the query and provided to the model as additional context. Adds $0.013 per call when invoked on top of the model’s normal token cost. Disabled by default.
disable_formattingbooleannofalseReturn the answer without the Sources list that web search adds.

Notes

Supports text and image input, streaming, function tools, structured JSON output, and reasoning strength control through reasoning_effort (none, low, medium, high, max). Reasoning defaults to high.

Machine-readable schema: GET https://api.empiriolabs.ai/v1/models/muse-glimmer-30b.